This repository was archived by the owner on Jan 15, 2024. It is now read-only.
Enable bias correction in AdamW when fine-tuning BERT#1468
Open
leezu wants to merge 1 commit intodmlc:masterfrom
Open
Enable bias correction in AdamW when fine-tuning BERT#1468leezu wants to merge 1 commit intodmlc:masterfrom
leezu wants to merge 1 commit intodmlc:masterfrom
Conversation
Mosbach, Marius, Maksym Andriushchenko, and Dietrich Klakow. "On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines." arXiv preprint arXiv:2006.04884 (2020). Zhang, Tianyi, et al. "Revisiting Few-sample BERT Fine-tuning." arXiv preprint arXiv:2006.05987 (2020).
Member
|
Let's try to rerun the training with the batch script here: https://github.com/dmlc/gluon-nlp/tree/master/tools/batch#squad-training Basically, we just need to run the following two for SQuAD 2.0 and 1.1 |
Codecov Report
@@ Coverage Diff @@
## master #1468 +/- ##
==========================================
- Coverage 85.86% 85.84% -0.02%
==========================================
Files 52 52
Lines 6911 6911
==========================================
- Hits 5934 5933 -1
- Misses 977 978 +1
Continue to review full report at Codecov.
|
|
The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1468/bertbiascorrection/index.html |
Contributor
Author
|
Member
|
Yes, you can later use the following script to sync up the results. After all results (part of the results) have been finished, you can parse the logs via |
Contributor
Author
Is there any known issue with Mobilebert? I |
Contributor
Author
|
Looks like an AMP issue or an operator issue causing AMP to continue decreasing the scale.. finetune_squad2.0.log |
Member
|
Yes.
Get Outlook for iOS<https://aka.ms/o0ukef>
…________________________________
From: Leonard Lausen <notifications@github.com>
Sent: Friday, January 8, 2021 6:11:53 AM
To: dmlc/gluon-nlp <gluon-nlp@noreply.github.com>
Cc: Xingjian SHI <xshiab@connect.ust.hk>; Review requested <review_requested@noreply.github.com>
Subject: Re: [dmlc/gluon-nlp] Enable bias correction in AdamW when fine-tuning BERT (#1468)
Looks like an AMP issue? finetune_squad2.0.log<https://github.com/dmlc/gluon-nlp/files/5787622/finetune_squad2.0.log>
—
You are receiving this because your review was requested.
Reply to this email directly, view it on GitHub<#1468 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ABHQH3SCBUACNO3HK254UOTSY4HCTANCNFSM4VZVBFMA>.
|
Member
|
From the figure, I think the performance looks similar. If we choose to update the flags, we can upload the pretrained weights to S3 and also change the numbers in https://github.com/dmlc/gluon-nlp/tree/master/scripts/question_answering. |
sxjscience
approved these changes
Jan 10, 2021
Member
sxjscience
left a comment
sxjscience
left a comment
There was a problem hiding this comment.
LGTM in general. We will also need to update the results table.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This should improve stability.
Mosbach, Marius, Maksym Andriushchenko, and Dietrich Klakow. "On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines." arXiv preprint arXiv:2006.04884 (2020).
Zhang, Tianyi, et al. "Revisiting Few-sample BERT Fine-tuning." arXiv preprint arXiv:2006.05987 (2020)